Central control system for digital multimedia exhibition hall

Abstract

The application discloses a digital multimedia exhibition hall central control system, and relates to the technical field of central control systems.The time-space correlation analysis module constructs a fault propagation probability atlas of exhibition hall equipment and audience behavior, the coupling degree analysis module verifies cross-layer causal relationships using a directional disturbance injection method based on the fault propagation probability atlas, the correlation matrix of resource scheduling operations and fault propagation chains is analyzed, the coupling degree index is fitted, the dynamic priority decision module fits the fault propagation cost gradient, the coupling degree index and the fault propagation cost gradient are input into the priority function, the synergistic priority of short-term suppression actions and long-term eradication actions is calculated, the execution sequence of the two types of actions is obtained, and the strategy execution module calls the execution sequence of the two types of actions through the central control platform interface and executes corresponding strategy actions.The central control system not only has strong dynamic adaptability, but also can respond to audience needs and equipment state changes in real time, improve exhibition management efficiency and enhance the immersive experience of audiences.

Description

Technical Field

[0001] This invention relates to the field of central control system technology, specifically to a central control system for a digital multimedia exhibition hall. Background Technology

[0002] With the rapid development of science and technology and the widespread application of information technology, traditional exhibition methods are gradually failing to meet the needs of modern audiences for interactive, immersive, and personalized experiences. Digital multimedia exhibition halls have emerged as a result. As a form of exhibition that integrates advanced technology and creative design, they provide a richer, more dynamic, and more diverse exhibition experience. However, with the increase in the types of equipment in exhibition halls and the increasing complexity of the content, how to efficiently manage and control these devices has become an urgent problem to be solved.

[0003] The existing technology has the following drawbacks:

[0004] Traditional central control systems lack the ability to automatically identify and verify causal relationships between devices, and also lack accurate modeling of fault propagation. Furthermore, most fault repair and emergency response mechanisms are based on static rule settings, lacking the ability to dynamically optimize and make real-time decisions. This makes it difficult to adjust and optimize operating strategies in a timely manner according to actual conditions, resulting in untimely or non-targeted implementation of repair measures, which is difficult to meet the ever-changing exhibition needs and audience behavior.

[0005] Based on this, the present invention proposes a central control system for digital multimedia exhibition halls, which not only has strong dynamic adaptability, but also can respond to audience needs and equipment status changes in real time, thereby improving exhibition management efficiency and enhancing the audience's immersive experience. Summary of the Invention

[0006] The purpose of this invention is to provide a central control system for a digital multimedia exhibition hall to address the shortcomings in the prior art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a central control system for a digital multimedia exhibition hall, comprising a cross-layer indicator perception module, a spatiotemporal correlation analysis module, a coupling degree analysis module, a dynamic priority decision-making module, and a strategy execution module;

[0008] The cross-layer indicator perception module collects various data in the exhibition hall environment in real time and forms a standardized set of cross-layer indicators;

[0009] The spatiotemporal correlation analysis module aligns the time series of data at different levels through an incremental time series alignment algorithm, and constructs a fault propagation probability map of exhibition hall equipment and visitor behavior based on a dynamic time window;

[0010] The coupling analysis module is based on the fault propagation probability map and uses the directional disturbance injection method to verify cross-layer causal relationships. By analyzing the correlation matrix between resource scheduling operations and fault propagation chains, it fits the coupling index, establishes coupling analysis rules, and generates root cause localization instructions for negative coupling scenarios.

[0011] The dynamic priority decision module fits the fault propagation cost gradient, and the coupling index and fault propagation cost gradient are input into the priority function to calculate the synergistic priority of short-term suppression actions and long-term eradication actions, and obtain the execution sequence of the two types of actions.

[0012] The strategy execution module calls the execution sequence of the two types of actions through the central control platform interface and executes the corresponding strategy actions.

[0013] In a preferred embodiment, the dynamic priority decision module analyzes the fault repair time and equipment response speed based on historical data to fit a fault propagation cost gradient.

[0014] The coupling degree index and the fault propagation cost gradient are input into the priority function to calculate the priority of short-term suppression actions and long-term eradication actions.

[0015] Based on the calculated priorities, execution sequences for short-term suppression actions and long-term eradication actions are generated respectively.

[0016] In a preferred embodiment, the expression for calculating the fault propagation cost gradient is: ,in, This represents the cost gradient of fault propagation. The resources required for fault repair For repair time, For equipment resource consumption, For equipment Repair time, This represents the total number of devices.

[0017] In a preferred embodiment, the expression for the priority function is: ,in, The overall priority of a certain action. and These are the weighting coefficients. For the fault propagation cost gradient, This is the coupling degree index.

[0018] In a preferred embodiment, the coupling analysis module simulates intervention in the displayed content using a targeted perturbation injection method, tests the impact of the displayed content on other system components, monitors the response of data at other levels, and verifies whether the causal relationship holds, in order to obtain the results at a given time point. Up equipment Regarding audience behavior The degree of coupling;

[0019] Identify the impact of equipment malfunctions or changes in displayed content on the exhibition effect and generate a correlation matrix;

[0020] A coupling index is generated based on different operations to quantify the impact of different operations on the exhibition effect. The higher the coupling index of a device, the higher its processing priority.

[0021] In a preferred embodiment, the acquisition at a time point Up equipment Regarding audience behavior The coupling degree is expressed as: ,in, Indicates a point in time Up equipment Regarding audience behavior The degree of coupling, For equipment With audience behavior Sensitivity coefficient between them For equipment At the point of time The amount of disturbance on;

[0022] The formula for calculating the coupling degree index is as follows: ,in, For the first Coupling index of individual devices For equipment With equipment The degree of correlation between them For equipment The change after the disturbance.

[0023] In a preferred embodiment, the spatiotemporal correlation analysis module aligns the time series of data at different levels using an incremental time series alignment algorithm, including the following steps:

[0024] By selecting a time reference point, low-frequency hardware resource data is interpolated to correspond to the timestamp of high-frequency data. The formula is as follows: ,in, For the aligned first Data at a specific time point The value, and They are the first Data at a specific time point and The original value, This represents the total length of the time interval.

[0025] In a preferred embodiment, the spatiotemporal correlation analysis module constructs a fault propagation probability map of exhibition hall equipment and visitor behavior, including the following steps:

[0026] A dynamic time window is obtained based on the rate of change of real-time data and the characteristics of fault propagation, and a fault propagation probability map is constructed within the dynamic time window;

[0027] After the fault propagation probability map is constructed, nodes with implicit associations are identified based on the relationship network between spatiotemporal data.

[0028] In a preferred embodiment, the cross-layer indicator perception module collects various types of data in the exhibition hall environment in real time, including the operating status of hardware resources, lifecycle events of display equipment, and audience interaction behavior at the application layer. After hierarchical labeling preprocessing and outlier filtering, a standardized set of cross-layer indicators is formed.

[0029] In a preferred embodiment, the operating status of the hardware resources includes the operating status of the exhibition hall server and network equipment, and the operating status of the network equipment includes CPU utilization, memory usage, and network latency.

[0030] The lifecycle events of the display equipment include the on / off status, usage duration, and brightness adjustment of the projector, LED screen, and interactive screen;

[0031] The audience interaction behavior in the application layer includes the frequency of touch screen clicks, location popularity, and VR device usage data.

[0032] The technical effects and advantages provided by the present invention in the above technical solution are as follows:

[0033] This invention utilizes a spatiotemporal correlation analysis module to align the temporal sequences of data at different levels using an incremental temporal alignment algorithm. Based on a dynamic time window, it constructs a fault propagation probability map of exhibition hall equipment and visitor behavior. A coupling analysis module, based on this probability map, verifies cross-layer causal relationships using a directional perturbation injection method. By analyzing the correlation matrix between resource scheduling operations and the fault propagation chain, it fits a coupling index and establishes coupling analysis rules to quantify the impact of different operations on the exhibition effect, generating root cause localization instructions for negatively coupled scenarios. A dynamic priority decision module fits the fault propagation cost gradient, and the coupling index and fault propagation cost gradient are input into a priority function to calculate the synergistic priority of short-term suppression actions and long-term eradication actions, deriving the execution sequences of the two types of actions. A strategy execution module calls the execution sequences of the two types of actions through the central control platform interface and executes the corresponding strategy actions. This central control system not only has strong dynamic adaptability but also can respond in real time to visitor needs and equipment status changes, improving exhibition management efficiency and the visitor's immersive experience. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0035] Figure 1 This is a block diagram of the central control system of the present invention. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0037] Example 1: Please refer to Figure 1 As shown, this embodiment provides a central control system for a digital multimedia exhibition hall, including a cross-layer indicator perception module, a spatiotemporal correlation analysis module, a coupling degree analysis module, a dynamic priority decision-making module, and a strategy execution module;

[0038] The cross-layer indicator perception module collects various data in the exhibition hall environment in real time, including the operating status of hardware resources (such as servers and network devices), life cycle events of display equipment (such as the usage of projectors, LED screens, and interactive screens), and audience interaction behaviors at the application layer (such as touch screen clicks and VR interactive data). After hierarchical labeling preprocessing and outlier filtering, a standardized cross-layer indicator set is formed, which is then sent to the spatiotemporal correlation analysis module.

[0039] The spatiotemporal correlation analysis module connects to the cross-layer indicator perception module and uses an incremental temporal alignment algorithm to address the temporal discrepancy problem between different levels of data (e.g., low-frequency acquisition of hardware resource data versus high-frequency acquisition of interactive behavior data). Based on a dynamic time window, it constructs a fault propagation probability map of exhibition hall equipment and visitor behavior, identifies implicit correlation nodes with spatiotemporal coupling characteristics between cross-layer indicators, and thus reveals potential factors that may affect the exhibition effect. The fault propagation probability map is then sent to the coupling degree analysis module.

[0040] The coupling degree analysis module uses a fault propagation probability graph and a directed perturbation injection method to verify the authenticity of cross-layer causal relationships. For example, it tests the impact of equipment failure on audience behavior or the impact of content issues on the exhibition experience. By analyzing the correlation matrix between resource scheduling operations and the fault propagation chain, a coupling degree index is fitted, and coupling degree analysis rules are established to quantify the impact of different operations on the exhibition effect. Root cause localization instructions for negatively coupled scenarios (such as equipment failure, content mismatch, etc.) are generated, and the coupling degree index is sent to the dynamic priority decision module.

[0041] The dynamic priority decision-making module analyzes historical exhibition fault repair times and equipment response speed data to fit a fault propagation cost gradient. The coupling index and fault propagation cost gradient are input into a priority function to calculate the synergistic priority of short-term suppression actions and long-term eradication actions. For example, regarding a current equipment fault, the priority can determine whether to repair the equipment immediately or temporarily replace it by optimizing the display content and interactive guidance, ultimately resulting in an execution sequence for the two types of actions. This execution sequence is then sent to the strategy execution module.

[0042] The strategy execution module invokes the execution sequence of two types of actions through the central control platform interface and executes the corresponding strategy actions. For example, if the system decides to repair faulty equipment, it will issue the corresponding command to perform the repair operation; if the system decides to optimize the content display, it will adjust the display content or provide new interactive solutions. The system dynamically adjusts the environment (such as lighting and sound) and display content in real time, and dynamically adjusts the exhibition hall display content and interactive methods based on visitor behavior data (such as dwell time and hotspot areas) to enhance visitor immersion and experience.

[0043] This application uses a spatiotemporal correlation analysis module to align the time series of data at different levels through an incremental time series alignment algorithm. Based on a dynamic time window, it constructs a fault propagation probability map of exhibition hall equipment and visitor behavior. A coupling analysis module, based on the fault propagation probability map, uses a directed perturbation injection method to verify cross-layer causal relationships. By analyzing the correlation matrix between resource scheduling operations and the fault propagation chain, it fits a coupling index and establishes coupling analysis rules to quantify the impact of different operations on the exhibition effect, generating root cause localization instructions for negatively coupled scenarios. A dynamic priority decision module fits the fault propagation cost gradient, and the coupling index and fault propagation cost gradient are input into a priority function to calculate the synergistic priority of short-term suppression actions and long-term eradication actions, deriving the execution sequences of the two types of actions. A strategy execution module calls the execution sequences of the two types of actions through the central control platform interface and executes the corresponding strategy actions. This central control system not only has strong dynamic adaptability but also can respond in real time to visitor needs and equipment status changes, improving exhibition management efficiency and the visitor's immersive experience.

[0044] Example 2: The cross-layer indicator perception module collects various data in the exhibition hall environment in real time, including the operating status of hardware resources (such as servers and network devices), life cycle events of display devices (such as the usage of projectors, LED screens, and interactive screens), and audience interaction behaviors at the application layer (such as touch screen clicks and VR interactive data). After hierarchical labeling preprocessing and outlier filtering, a standardized cross-layer indicator set is formed, which is then sent to the spatiotemporal correlation analysis module.

[0045] The primary task of the cross-layer indicator perception module is to monitor and collect various important data in the exhibition hall environment in real time. Firstly, by deploying multiple data acquisition sensors and probes, this module covers multiple dimensions from hardware resources to the application layer. Specifically, the hardware resource layer includes, but is not limited to, the operating status of exhibition hall servers and network equipment, such as CPU utilization, memory usage, and network latency. These are fundamental data ensuring the stable operation of the exhibition hall's central control system. The display equipment layer collects data on equipment lifecycle events, such as the on / off status, usage duration, and brightness adjustment of projectors, LED screens, and interactive screens. This data provides direct evidence for monitoring the health status of the equipment. The application layer focuses on audience interaction behavior, such as touchscreen click frequency, location popularity, and VR device usage data. This data helps analyze audience behavior patterns and the popularity of exhibition content.

[0046] After collecting this multi-dimensional data, it needs to undergo hierarchical labeling preprocessing. The purpose of hierarchical labeling is to effectively tag the data according to its source level (hardware resources, display devices, application layer) and to adapt it according to the characteristics of different levels. Data at each level is organized by time series to ensure that the data can be aligned and compared with data from other levels in a precise time sequence. During preprocessing, the module also performs outlier filtering on the collected data to remove invalid or extreme data points, ensuring the accuracy and reliability of the final data. The main basis for outlier filtering is to set a threshold using statistical methods; if a data point deviates too much from this threshold, the data will be considered an anomaly and removed.

[0047] After data preprocessing, a standardized set of cross-level metrics is formed. This set is a multi-dimensional, cross-level dataset covering various aspects such as hardware resources, display equipment, and audience interaction data. The purpose of standardization is to transform data from different data sources into a unified metric, ensuring seamless data exchange between different levels. The standardization formula can be expressed as: ,in, For the first The observation data at the ... The original values ​​at each level For the first The mean of data at each level For the first The standard deviation of the data at each level. This formula normalizes the data at each level to conform to a standard normal distribution. This ensures that data from different sources can be analyzed and calculated under the same standard.

[0048] After forming a standardized set of cross-layer indicators, the module sends this set to the spatiotemporal correlation analysis module for subsequent time series alignment and fault propagation analysis. This set not only provides multidimensional data support for spatiotemporal correlation analysis but also lays the data foundation for fault prediction, dynamic optimization, and decision-making.

[0049] The spatiotemporal correlation analysis module connects to the cross-layer indicator perception module and uses an incremental temporal alignment algorithm to address the temporal discrepancy problem between different levels of data (e.g., low-frequency acquisition of hardware resource data versus high-frequency acquisition of interactive behavior data). Based on a dynamic time window, it constructs a fault propagation probability map of exhibition hall equipment and visitor behavior, identifies implicit correlation nodes with spatiotemporal coupling characteristics between cross-layer indicators, and thus reveals potential factors that may affect the exhibition effect. The fault propagation probability map is then sent to the coupling degree analysis module.

[0050] The core function of the spatiotemporal correlation analysis module is to solve the problem of temporal alignment of data at different levels by deeply analyzing the data provided by the cross-layer indicator perception module, and to construct a fault propagation probability map based on this to reveal potential fault propagation paths in the exhibition. First, the spatiotemporal correlation analysis module needs to address the temporal differences between data at different levels, especially when there is a significant temporal discrepancy between hardware resource data and audience interaction behavior data. Hardware resource data (such as server CPU load and memory usage) is typically collected at low frequencies, while application-layer audience interaction behavior data (such as touchscreen click frequency and VR interaction behavior) is collected at high frequencies, leading to temporal inconsistencies between the two types of data. To solve this problem, the spatiotemporal correlation analysis module employs an incremental temporal alignment algorithm to gradually align data from different time intervals.

[0051] The key idea of ​​the incremental time-series alignment algorithm is to match data using timestamps and interpolate low-frequency data to ensure that data at different levels can be compared and analyzed on a unified time scale. The specific algorithm steps are as follows: First, select a time reference point (e.g., the timestamp of audience interaction data). Then, interpolate low-frequency hardware resource data to correspond to the timestamps of high-frequency data. The formula is expressed as: ,in, For the aligned first Data at a specific time point The value, and They are the first Data at a specific time point and The original value, This represents the total length of the time interval. The formula achieves time-series alignment of low-frequency data through linear interpolation. In this way, the module unifies data from different levels onto a single time axis, eliminating time skew and improving the comparability of data.

[0052] In the central control system of a digital multimedia exhibition hall, the system needs to process time-series data at different levels, including operational data of exhibition equipment (such as projectors and interactive screens) and data on audience interaction behavior. The data collection frequency of the equipment may be low (e.g., once per minute), while the data collection frequency of audience interaction may be high (e.g., once per second). This difference leads to time-series deviations between the two types of data, directly affecting the system's analytical effectiveness and decision-making accuracy.

[0053] First, a time reference is selected (e.g., the time point of audience interaction data). In this case, audience interaction data is used as the reference time point, assuming audience behavior data is collected once per second. Next, device data needs to be time-aligned, as the device data is collected at a lower frequency, perhaps once per minute. Therefore, an incremental time-alignment algorithm is used to interpolate or resample this low-frequency data to align it with the time of the high-frequency audience behavior data.

[0054] Suppose we have the following two time series data:

[0055] Audience interaction data (collected once per second): ;

[0056] Equipment operating data (collected once per minute): .

[0057] Device data is time-aligned to ensure that at each point in time, the device data matches the time frame of the audience interaction data. To achieve this, an incremental time-series alignment algorithm interpolates the device data to fit the time frame of the audience interaction data.

[0058] In this way, the incremental time-series alignment algorithm can effectively eliminate the time deviation between device data and audience behavior data, ensuring that all data can be compared and analyzed on a unified time axis, providing an accurate basis for subsequent fault prediction, optimization decisions, and other tasks.

[0059] Next, the spatiotemporal correlation analysis module constructs a fault propagation probability map between exhibition hall equipment and visitor behavior using dynamic time window technology. This map represents the potential fault propagation paths between various equipment and visitor behaviors in the exhibition hall; that is, how a fault in one piece of equipment affects other equipment and visitor behavior. The dynamic time window is the time scale used to analyze the duration of an event and its propagation effect; it can be flexibly adjusted according to real-time data changes. The size of the dynamic time window typically depends on the rate of change of real-time data and the characteristics of fault propagation, and can be defined by the following formula: ,in, For the time window of fault propagation, This is the current time of the fault. This represents the maximum duration of the fault. By dynamically adjusting the window, the system can adaptively capture critical moments in the fault propagation process, providing accurate propagation paths and probabilities.

[0060] A digital central control system has been deployed in a modern technology exhibition hall, encompassing multiple display devices and interactive areas for visitors. The system monitors the operational status of the equipment, malfunctions, and visitor interactions in real time. Its aim is to use a spatiotemporal correlation analysis module to provide early warnings of potential equipment failures, thereby optimizing the visitor experience. For example, consider a display projector in one exhibit area, whose performance is closely linked to visitor behavior (e.g., the number of clicks on interactive screens). A projector malfunction during the exhibition could impact visitor interaction. Therefore, the system needs to use the spatiotemporal correlation analysis module to capture the propagation path of the equipment failure and predict potential malfunctions in other devices.

[0061] When a projector malfunctions, the system monitors changes in audience interaction behavior in real time using a dynamic time window. If a significant change in audience interaction frequency occurs at the time of the malfunction (e.g., a sharp drop in click frequency), it indicates a substantial impact on the exhibition, requiring priority handling of the malfunction. Through a spatiotemporal correlation analysis module, the system can calculate the propagation path of the impact between different devices. For example, a projector malfunction might initially affect the click frequency of the interactive screen, further impacting the device response in the VR interactive area. Based on the fault propagation map, the system can track the impact of the device malfunction on other devices and calculate the speed and extent of fault propagation.

[0062] The window length for fault propagation will be used to quantify the impact of device failures on viewer behavior. For example, assuming that the frequency of interaction with VR devices also decreases after a projector failure, the system will analyze this data to generate a predictive model to assess the possible timing and impact of failures in other devices.

[0063] After constructing the fault propagation probability map, the spatiotemporal correlation analysis module reveals potential relationships between data at different levels by identifying spatiotemporal coupling nodes in the data. These coupling characteristics are often difficult to discover through simple data analysis methods. Therefore, the module needs to identify nodes with implicit relationships based on the relationship network between spatiotemporal data. These implicit nodes usually represent key events in equipment failure or audience behavior, and changes in these nodes may have a significant impact on the exhibition effect.

[0064] Finally, the spatiotemporal correlation analysis module sends the constructed fault propagation probability map to the coupling degree analysis module, providing data support for subsequent verification of fault causality and root cause localization. The spatiotemporal coupling characteristics and implicit correlation nodes contained in the map provide important evidence for early warning and impact assessment of faults, ensuring that the central control system can quickly identify potential problems and take corresponding intervention strategies.

[0065] The coupling degree analysis module uses a fault propagation probability graph and a directed perturbation injection method to verify the authenticity of cross-layer causal relationships. For example, it tests the impact of equipment failure on audience behavior or the impact of content issues on the exhibition experience. By analyzing the correlation matrix between resource scheduling operations and the fault propagation chain, a coupling degree index is fitted, and coupling degree analysis rules are established to quantify the impact of different operations on the exhibition effect. Root cause localization instructions for negatively coupled scenarios (such as equipment failure, content mismatch, etc.) are generated, and the coupling degree index is sent to the dynamic priority decision module.

[0066] The core function of the coupling analysis module is to deeply verify the authenticity of cross-layer causal relationships based on the fault propagation probability map generated by the spatiotemporal correlation analysis module. It also quantifies the impact of different operations on the exhibition effect by fitting a coupling index to the correlation matrix between resource scheduling operations and the fault propagation chain. This module primarily verifies the causal relationships between devices and between devices and audience behavior through a directional perturbation injection method, ultimately generating root cause localization instructions.

[0067] First, the coupling analysis module simulates intervention in the displayed content using a targeted perturbation injection method to test its impact on other system components. For example, the system can simulate a projector malfunction to see if it leads to a decrease in audience interaction frequency or if problems with the displayed content cause a loss of audience interest. This process verifies causality by introducing perturbations (such as shutting down a device or changing the displayed content) and monitoring the responses of other levels of data (such as audience behavior data and device operating status). The formulaic expression of this process is as follows: ,in, Indicates a point in time Up equipment Regarding audience behavior The degree of coupling, For equipment With audience behavior Sensitivity coefficient between them For equipment At the point of time The disturbance amount is calculated as follows: (For example, if at a certain moment the projection equipment malfunctions, causing its brightness to decrease by 20%, and this decrease in brightness affects the audience's interactive behavior, resulting in a 10% reduction in touchscreen clicks, then the disturbance amount is -10%). This formula is used to quantify the impact of equipment malfunctions or content changes on audience behavior.

[0068] In this application, the equipment With audience behavior Sensitivity coefficient between The calculation logic is as follows:

[0069] Taking the impact of projection brightness on the number of touch screen clicks as an example, if the following data exists, as shown in Table 1:

[0070] Table 1: Examples of Impact

[0071]

[0072] The sensitivity coefficient is estimated using the least squares method, which minimizes the sum of squared errors. The expression is: ,in: This is the number of data points (6 in this example). and They represent the first The projected brightness and touchscreen click count of each data point are used to calculate the sensitivity coefficient using the formula. Therefore, the sensitivity coefficient That is, for every 1% decrease in projection brightness, the number of touch screen clicks will decrease by 1.55 times per hour.

[0073] By analyzing the relationship between targeted perturbation injection and data response, the module can effectively identify the impact of equipment failures or changes in displayed content on the exhibition effect. In particular, through the correlation matrix between resource scheduling operations and the fault propagation chain, the system can more clearly understand the interaction relationships between various devices and assess the propagation effect of faults. The correlation matrix is ​​expressed as follows: , where represents Indicates equipment and equipment The degree of correlation between them and respectively equipment and equipment The state vector, Indicates equipment and equipment The dot product of the state vectors, and These are the norms of the device state vectors. Using this method, the module can reveal potential dependencies between devices and their synergistic effects under failure conditions.

[0074] Through further analysis, the system can generate a coupling index based on different operations (such as equipment failure, content mismatch, etc.). This index quantifies the impact of different operations on the exhibition effect and generates root cause localization instructions when encountering negative coupling scenarios. The root cause localization instructions specifically indicate which repair or adjustment operations the system needs to perform, such as repairing a faulty device, adjusting the display content, or optimizing the interactive design to restore the exhibition effect. The formula for calculating the coupling index is: ,in, For the first Coupling index of individual devices For equipment With equipment The degree of correlation between them For equipment The change after the disturbance, where N represents the total number of devices. By calculating the coupling index of all devices, the system can determine which devices have the most significant impact on the exhibition effect, and thus prioritize processing these devices.

[0075] In a digital multimedia exhibition hall, there are various display devices, including projectors, touchscreens, and sound systems. The system monitors the real-time operating status of these devices (such as brightness, volume, and touch response) and analyzes the impact of device malfunctions or adjustments on the visitor experience. Devices and operations: Device 1: Projector, Device 2: Touchscreen, Device 3: Sound system. Assume that a projector malfunction causes a decrease in brightness, a slowdown in touchscreen response, and a decrease in sound system volume. The goal is to quantify the impact of these operations on the exhibition effect by calculating a comprehensive coupling index and prioritize repairing the devices with the greatest impact.

[0076] Indicates equipment and equipment The correlation between them. Assume the correlation between the projector and the touch screen is 0.6, the correlation between the projector and the sound system is 0.4, and the correlation between the touch screen and the sound system is 0.5. Indicates equipment The changes after the disturbance. For example, the projector brightness decreases by 2096, the touchscreen response time increases by 10%, and the speaker volume decreases by 15%. This represents the total number of devices, which is 3 here (projector, touchscreen, and sound system).

[0077] The formula for calculating the coupling index of a projector is: Substitute the values: ,here, This represents the degree of correlation between the projector and the touchscreen. This represents the degree of correlation between the projector and the sound system. This represents a 10% increase in touchscreen response time. This represents a 15% decrease in the volume of the audio system.

[0078] By calculating the overall coupling degree index, the system can prioritize repairing the equipment with the greatest impact based on the highest coupling degree. If a projector malfunction has the greatest impact on the exhibition effect, the system will prioritize repairing the projector. Assuming the coupling degree of the sound system is 6% and the coupling degree of the touch screen is 8%, the system will generate adjustment instructions in the following order based on the calculated coupling degrees: prioritize repairing the projector; adjust the response speed of the touch screen; adjust the volume of the sound system.

[0079] Finally, the generated coupling index is sent to the dynamic priority decision-making module for subsequent fault repair and exhibition optimization decisions. Through the precise analysis of this module, the system can respond quickly and effectively to equipment failures or display content issues, ensuring the smooth operation of the exhibition.

[0080] The dynamic priority decision-making module analyzes historical exhibition fault repair times and equipment response speed data to fit a fault propagation cost gradient. The coupling index and fault propagation cost gradient are input into a priority function to calculate the synergistic priority of short-term suppression actions and long-term eradication actions. For example, regarding a current equipment fault, the priority can determine whether to repair the equipment immediately or temporarily replace it by optimizing the display content and interactive guidance, ultimately resulting in an execution sequence for the two types of actions. This execution sequence is then sent to the strategy execution module.

[0081] The core task of the dynamic prioritization decision-making module is to calculate the cost gradient of fault propagation based on historical fault repair times, equipment response speeds, and other system parameters. Then, based on this gradient and the coupling index, it optimizes the collaborative priority of short-term containment actions and long-term eradication actions. The key to this module is its data-driven approach, determining which problems require immediate repair and which can be temporarily replaced by optimizing display content or interactive methods, thereby maximizing the exhibition's effectiveness.

[0082] First, the dynamic prioritization decision module analyzes fault repair time and equipment response speed based on historical data. This historical data can be obtained by analyzing the repair time and equipment response time after each fault occurred. For example, the time to repair a projection device may differ significantly from the time to repair a touchscreen device. The system will fit a fault propagation cost gradient based on this historical data. This cost gradient reflects the impact of equipment failure on the entire exhibition, including time costs, resource waste, and loss of audience experience. The fault propagation cost gradient can be expressed by the following formula: ,in, This represents the cost gradient of fault propagation. The resources required for fault repair For repair time, For equipment resource consumption, For equipment Repair time, This represents the total number of devices. This formula is used to measure the overall impact of repair time and resource consumption on the exhibition.

[0083] Next, the dynamic priority decision module inputs the coupling degree index and the fault propagation cost gradient into the priority function. The priority function calculates the priority of short-term mitigation actions (such as temporary replacements or adjusting display content) versus long-term eradication actions (such as equipment repair or replacement) based on the type of the current fault and its potential impact on the exhibition effect. Through this function, the system can dynamically adjust the relative priority of the two types of actions. For example, for equipment faults with minor impact, the system may prioritize temporary replacements; while for equipment faults with significant impact, the system may immediately initiate the equipment repair process.

[0084] The expression for the precedence function is: ,in, The overall priority of a certain action. and These are the weighting coefficients. For the fault propagation cost gradient, This is the coupling degree index. and These parameters are adjusted based on historical data and actual needs. The formula calculates the highest priority action by comprehensively considering failure costs and coupling index, thereby guiding the system to select the most suitable operational plan.

[0085] Based on the calculated priorities, the system can generate execution sequences for short-term suppression actions and long-term eradication actions. For example, if a device malfunctions and its propagation cost is high, the system will prioritize device repair tasks; if the malfunction has a minor impact on the exhibition effect, temporary alternatives can be selected, such as adjusting the display content or optimizing the interaction methods.

[0086] Ultimately, the dynamic priority decision-making module sends the execution sequence of these two types of actions to the strategy execution module. The strategy execution module then performs specific operations based on these instructions, such as issuing repair commands or adjusting the displayed content through the central control system interface. Through this combination of intelligent decision-making and execution, the system ensures the smooth operation of the exhibition and maximizes the visitor experience.

[0087] By comprehensively analyzing historical fault repair times, equipment response speeds, fault propagation costs, and coupling indices, the dynamic priority decision-making module can intelligently optimize the priorities of short-term suppression and long-term eradication actions, enabling timely and effective handling of problems during exhibitions and improving the overall display effect. This mechanism not only enhances the system's response speed but also makes resource utilization more efficient and precise.

[0088] The strategy execution module invokes the execution sequence of two types of actions through the central control platform interface and executes the corresponding strategy actions. For example, if the system decides to repair faulty equipment, it will issue the corresponding command to perform the repair operation; if the system decides to optimize the content display, it will adjust the display content or provide new interactive solutions. The system dynamically adjusts the environment (such as lighting and sound) and display content in real time, and dynamically adjusts the exhibition hall display content and interactive methods based on visitor behavior data (such as dwell time and hotspot areas) to enhance visitor immersion and experience.

[0089] The strategy execution module is a key component of the digital multimedia exhibition hall's central control system. It is responsible for executing the actual operations based on the execution sequence output by the dynamic priority decision-making module. Through tight integration with the central control platform interface, this module ensures that decision results are quickly and accurately translated into specific actions, thereby guaranteeing the smooth operation of the exhibition and optimizing the visitor experience. Its operation process mainly includes equipment repair, content display optimization, and environmental adjustments, as detailed below:

[0090] First, when the system decides to repair faulty equipment, the strategy execution module issues a repair command and initiates the corresponding maintenance process based on the equipment type and priority. For example, if display equipment such as a projector or touchscreen malfunctions, the system will automatically dispatch maintenance personnel or activate backup equipment through the central control platform interface. This process is monitored in real time to ensure that the equipment is restored to operation in the shortest possible time to avoid long-term impact on the visitor experience. The system judges the progress of fault repair based on real-time data and ensures that the display effect in the exhibition hall is as unaffected as possible during the repair process.

[0091] Secondly, when optimizing content display, the strategy execution module adjusts the exhibition content and interactive display methods in real time based on information such as audience interaction data, dwell time, and hot spots. Through precise monitoring of audience behavior, the system can identify which exhibits are more popular and which content receives less interaction, thus dynamically adjusting the displayed content. For example, if audiences spend a long time in a particular exhibit area, the system may automatically enlarge the exhibit's display area or enhance interactive methods to further attract audience attention. Conversely, if an exhibit area fails to attract audience interest, the system may reduce the display intensity of that area and dynamically adjust the content or display methods to re-attract audience attention.

[0092] These adjustments are not limited to content but also include the control of the exhibition environment. For example, by adjusting parameters such as lighting, sound, temperature, and humidity in the exhibition hall in real time, the system can provide visitors with a more personalized viewing experience. Based on visitor behavior data, the system can dynamically identify the most suitable environmental atmosphere, such as increasing or decreasing light intensity, adjusting the volume and type of the sound system, and even adjusting the atmosphere to match the current exhibit.

[0093] The strategy execution module also optimizes interaction methods in real time based on audience behavior data and interaction patterns. For example, if the system detects low interaction frequency during interactive sessions, it may use prompts, reward mechanisms, or content display guidance to encourage audience participation and enhance their experience. To ensure a personalized audience experience, the system provides personalized recommendations based on audience interests and behaviors, further enhancing the interactivity and immersion of the exhibition.

[0094] Through the above multiple operational steps, the strategy execution module is not just a component that executes instructions, but an intelligent adjustment system that can optimize exhibition content and environmental settings based on real-time feedback, ensuring that each link can be carried out accurately and efficiently, thereby enhancing the audience's immersion and experience.

[0095] The strategy execution module, through its highly integrated and real-time feedback mechanism, ensures the automation and precision of fault repair, display content optimization, and environmental control. By dynamically monitoring and analyzing audience behavior data, environmental data, and equipment data, this module can intelligently adjust exhibition content and exhibition hall atmosphere, enhancing the overall audience experience and ensuring the smooth operation of exhibition activities.

[0096] Example 3: With the development of modern exhibition technology, digital multimedia exhibition halls have become an indispensable part of various exhibition activities. Traditional exhibition methods can no longer meet the high demands of contemporary audiences for interactivity and immersion. Therefore, the central control system in a digital multimedia exhibition hall has become the core for improving exhibition effects and audience experience. Through real-time data acquisition, analysis, and processing, the digital central control system can automatically adjust the exhibition content, display equipment, and exhibition hall environment to achieve the best display effect.

[0097] This technical solution targets the central control system of a digital multimedia exhibition hall. It integrates a cross-layer indicator perception module, a spatiotemporal correlation analysis module, a coupling degree analysis module, a dynamic priority decision-making module, and a strategy execution module. Through the collaborative work of these modules, real-time optimization of the exhibition effect is achieved. The following are detailed scenario examples of this system in practical applications.

[0098] A digital central control system was deployed in a modern technology exhibition hall. The hall contained multiple exhibit areas, including a virtual reality (VR) experience area, an interactive touchscreen display area, a projection display area, and traditional display walls. To provide the best visitor experience, the hall's environment, such as lighting, sound, temperature, and humidity, also needed to be adjusted in real time.

[0099] The cross-layer indicator sensing module collects various data in the exhibition hall environment in real time, including hardware resources, display equipment, and visitor interaction behavior. Below are examples of several main data collection categories:

[0100] Hardware Resource Layer: Collects operational status data from hardware resources such as servers, network devices, and projectors. For example, projector brightness, network latency, and CPU load. Example data: Projector brightness: 80% (normal value), network latency: 100ms, and server CPU utilization: 75%.

[0101] Display Equipment Layer: Acquire lifecycle data for display equipment, such as equipment on / off status, usage duration, and maintenance records. Example data: LED screen usage duration: 500 hours; projector on / off count: 40 times.

[0102] Application Layer: Viewer interaction data, including statistics on touchscreen clicks, VR interactions, etc. Example data: Touchscreen clicks: 350 times / hour, VR interactions: 60 times / hour. After preprocessing, this data generates a standardized set of cross-layer indicators and is sent to the spatiotemporal correlation analysis module.

[0103] The spatiotemporal correlation analysis module utilizes an incremental time-series alignment algorithm to address the time-series discrepancies between different data levels. For example, hardware resource data is collected at a low frequency, while audience behavior data is collected at a high frequency. The incremental time-series alignment method synchronizes these data to the same time window, creating comparable time-series data.

[0104] For example, after aligning the low-frequency data and high-frequency interaction data of hardware resources, the following timing data is generated, as shown in Table 2:

[0105] Table 2: Time Series Data Table

[0106]

[0107] Based on this time-series data, the spatiotemporal correlation analysis module constructs a fault propagation probability map, identifying potential spatiotemporal coupling relationships between devices and audience behavior. For example, a decrease in projector brightness may lead to reduced audience interaction, thereby affecting the exhibition experience.

[0108] The coupling analysis module, based on the fault propagation probability map generated by the spatiotemporal correlation analysis module, uses a directed perturbation injection method to verify the authenticity of cross-layer causal relationships. For example, it tests the impact of equipment malfunctions on visitor behavior, or the impact of issues with exhibit content on the exhibition experience.

[0109] If audience interaction decreases after a projector malfunction, the system verifies the impact of the malfunction on audience behavior through perturbation injection and calculates the coupling degree index using the correlation matrix. The perturbation amount for the projector malfunction is set as follows: The change in audience behavior is: The coupling index is calculated using the following formula: ,in, To determine the correlation between the projector and interactive behavior, This represents the change in audience interaction behavior. This coupling index indicates that reduced interaction due to projector malfunction has a significant negative impact on the exhibition experience.

[0110] The dynamic priority decision-making module analyzes the propagation cost gradient of exhibition failures based on historical data and the current coupling index, and calculates the synergistic priority of short-term suppression actions and long-term eradication actions according to the priority function.

[0111] For projector malfunctions, the system analyzes historical data such as repair time and device response speed to fit a fault propagation cost gradient. Assuming historical data indicates a projector repair time of 30 minutes and a repair cost of 100 units of resources, the system calculates the propagation cost gradient as follows: Then, the system inputs the coupling degree exponent and the fault propagation cost gradient into the priority function to calculate the priority of the two types of actions. Assume the priority function is:

[0112] ,in, , The priorities of short-term suppression and long-term eradication actions were calculated. Ultimately, repairing the equipment was deemed to have a higher priority.

[0113] The strategy execution module executes corresponding strategy actions based on the output of the dynamic priority decision module. If the system decides to repair faulty equipment, it issues a repair command through the central control platform interface; if the system decides to optimize the displayed content, it adjusts the displayed content or provides new interactive solutions.

[0114] If the system decides to repair the projector, it will issue a repair command through the central control platform and arrange for staff to perform equipment maintenance. Simultaneously, the system will adjust the exhibition hall's environmental settings in real time, such as lighting and sound, to optimize the visitor experience, as shown in Table 3.

[0115] Table 3: Relationship between Equipment and Exhibition Effectiveness

[0116]

[0117] Through the central control system of the digital multimedia exhibition hall, exhibition managers can monitor the exhibition environment in real time, dynamically adjust equipment and display content, and enhance the audience's immersion and interactivity. The system, through the collaborative work of its various modules, can accurately identify potential problems, make rapid decisions, and implement corresponding repair or optimization measures in the shortest possible time. Through a data-driven decision-making mechanism, the digital exhibition hall can maximize the exhibition's effectiveness, ensuring that every visitor enjoys a high-quality exhibition experience.

[0118] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0119] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A central control system for a digital multimedia exhibition hall, characterized in that: It includes a cross-layer indicator perception module, a spatiotemporal correlation analysis module, a coupling degree analysis module, a dynamic priority decision-making module, and a strategy execution module; The cross-layer indicator perception module collects various data in the exhibition hall environment in real time and forms a standardized set of cross-layer indicators; The spatiotemporal correlation analysis module aligns the time series of data at different levels using an incremental time series alignment algorithm, and is expressed based on a dynamic time window as follows: ,in, For the time window of fault propagation, This is the current time of the fault. To determine the maximum duration of the fault, a probability map of fault propagation for exhibition hall equipment and visitor behavior is constructed. The coupling analysis module is based on the fault propagation probability map and uses the directional disturbance injection method to verify cross-layer causal relationships. By analyzing the correlation matrix between resource scheduling operations and fault propagation chains, it fits the coupling index, establishes coupling analysis rules, and generates root cause localization instructions for negative coupling scenarios. The coupling analysis module simulates intervention in the displayed content using a targeted perturbation injection method, tests the impact of the displayed content on other system components, monitors the response of data at other levels, and verifies whether the causal relationship holds, in order to obtain the results at a given time point. Up equipment Regarding audience behavior The coupling degree is expressed as: ,in, Indicates a point in time Up equipment Regarding audience behavior The degree of coupling, For equipment With audience behavior Sensitivity coefficient between them For equipment At the point of time The amount of disturbance on; The sensitivity coefficient is estimated by minimizing the sum of squared errors. The expression is: ,in: It is the number of data points. and They represent the first The projection brightness and touchscreen click count of each data point; Identify the impact of equipment malfunctions or changes in displayed content on the exhibition effect and generate a correlation matrix; A coupling index is generated based on different operations to quantify the impact of different operations on the exhibition effect. The higher the coupling index of a device, the higher the processing priority of that device. The dynamic priority decision module fits the fault propagation cost gradient, expressed as: ,in, This represents the cost gradient of fault propagation. The resources required for fault repair For repair time, For equipment resource consumption, For equipment Repair time, Given the total number of devices, the coupling index, and the fault propagation cost gradient, the priority function is expressed as follows: ,in, The overall priority of a certain action. and These are the weighting coefficients, and and These parameters are adjusted based on historical data and actual needs. For the fault propagation cost gradient, The coupling degree index is defined by the following formula: ,in, For the first Coupling index of individual devices For equipment With equipment The degree of correlation between them For equipment The change after the disturbance is expressed in the form of the correlation matrix as follows: ,in, Indicates device and equipment The degree of correlation between them and respectively equipment and equipment The state vector, Indicates device and equipment The dot product of the state vectors, and The norms of the device state vectors are used to calculate the collaborative priority of short-term suppression actions and long-term eradication actions, and to obtain the execution sequence of the two types of actions. The strategy execution module calls the execution sequence of the two types of actions through the central control platform interface and executes the corresponding strategy actions; The spatiotemporal correlation analysis module aligns the time series of data at different levels using an incremental time series alignment algorithm, including the following steps: By selecting a time reference point, low-frequency hardware resource data is interpolated to correspond to the timestamp of high-frequency data. The formula is as follows: ,in, For the aligned first Data at a specific time point The value, and They are the first Data at a specific time point and The original value, This represents the total length of the time interval.

2. The central control system for a digital multimedia exhibition hall according to claim 1, characterized in that: The dynamic priority decision module analyzes the fault repair time and equipment response speed based on historical data and fits the fault propagation cost gradient. The coupling degree index and the fault propagation cost gradient are input into the priority function to calculate the priority of short-term suppression actions and long-term eradication actions. Based on the calculated priorities, execution sequences for short-term suppression actions and long-term eradication actions are generated respectively.

3. The central control system for a digital multimedia exhibition hall according to claim 2, characterized in that: The spatiotemporal correlation analysis module constructs a fault propagation probability map of exhibition hall equipment and visitor behavior, including the following steps: A dynamic time window is obtained based on the rate of change of real-time data and the characteristics of fault propagation, and a fault propagation probability map is constructed within the dynamic time window; After the fault propagation probability map is constructed, nodes with implicit associations are identified based on the relationship network between spatiotemporal data.

4. The central control system for a digital multimedia exhibition hall according to claim 1, characterized in that: The cross-layer indicator perception module collects various data in the exhibition hall environment in real time, including the operating status of hardware resources, life cycle events of display equipment, and audience interaction behavior at the application layer. After hierarchical labeling preprocessing and outlier filtering, a standardized set of cross-layer indicators is formed.

5. The central control system for a digital multimedia exhibition hall according to claim 4, characterized in that: The operating status of the hardware resources includes the operating status of the exhibition hall server and network equipment. The operating status of the network equipment includes CPU utilization, memory usage, and network latency. The lifecycle events of the display equipment include the on / off status, usage duration, and brightness adjustment of the projector, LED screen, and interactive screen; The audience interaction behavior in the application layer includes the frequency of touch screen clicks, location popularity, and VR device usage data.

Images